Add trace points into enqueue_task() and dequeue_task(). They are useful to
implement RV monitor which validates RT scheduling.

Signed-off-by: Nam Cao <namcao@linutronix.de>
---
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
---
v3: fix up build issue on !SMP
v2: Move the tracepoints to cover all task enqueue/dequeue, not just RT
---
 include/trace/events/sched.h | 13 +++++++++++++
 kernel/sched/core.c          |  8 +++++++-
 2 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 7b2645b50e78..696d22af5a98 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -896,6 +896,19 @@ DECLARE_TRACE(sched_set_need_resched,
 	TP_PROTO(struct task_struct *tsk, int cpu, int tif),
 	TP_ARGS(tsk, cpu, tif));
 
+/*
+ * The two trace points below may not work as expected for fair tasks due
+ * to delayed dequeue. See:
+ * https://lore.kernel.org/lkml/179674c6-f82a-4718-ace2-67b5e672fdee@amd.com/
+ */
+DECLARE_TRACE(enqueue_task,
+	TP_PROTO(int cpu, struct task_struct *task),
+	TP_ARGS(cpu, task));
+
+DECLARE_TRACE(dequeue_task,
+	TP_PROTO(int cpu, struct task_struct *task),
+	TP_ARGS(cpu, task));
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index be00629f0ba4..6367799aa023 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2077,6 +2077,8 @@ unsigned long get_wchan(struct task_struct *p)
 
 void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 {
+	trace_enqueue_task_tp(cpu_of(rq), p);
+
 	if (!(flags & ENQUEUE_NOCLOCK))
 		update_rq_clock(rq);
 
@@ -2119,7 +2121,11 @@ inline bool dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 	 * and mark the task ->sched_delayed.
 	 */
 	uclamp_rq_dec(rq, p);
-	return p->sched_class->dequeue_task(rq, p, flags);
+	if (p->sched_class->dequeue_task(rq, p, flags)) {
+		trace_dequeue_task_tp(cpu_of(rq), p);
+		return true;
+	}
+	return false;
 }
 
 void activate_task(struct rq *rq, struct task_struct *p, int flags)
-- 
2.39.5

On Mon, 2025-08-11 at 10:40 +0200, Nam Cao wrote:
> Add trace points into enqueue_task() and dequeue_task(). They are
> useful to implement RV monitor which validates RT scheduling.
> 
> Signed-off-by: Nam Cao <namcao@linutronix.de>
> ---

Peter, Ingo, this patch adds new tracepoints in the scheduler do agree
with the change, can we get an Ack?

Thanks,
Gabriele

> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Juri Lelli <juri.lelli@redhat.com>
> Cc: Vincent Guittot <vincent.guittot@linaro.org>
> Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
> Cc: Ben Segall <bsegall@google.com>
> Cc: Mel Gorman <mgorman@suse.de>
> Cc: Valentin Schneider <vschneid@redhat.com>
> Cc: K Prateek Nayak <kprateek.nayak@amd.com>
> ---
> v3: fix up build issue on !SMP
> v2: Move the tracepoints to cover all task enqueue/dequeue, not just
> RT
> ---
>  include/trace/events/sched.h | 13 +++++++++++++
>  kernel/sched/core.c          |  8 +++++++-
>  2 files changed, 20 insertions(+), 1 deletion(-)
> 
> diff --git a/include/trace/events/sched.h
> b/include/trace/events/sched.h
> index 7b2645b50e78..696d22af5a98 100644
> --- a/include/trace/events/sched.h
> +++ b/include/trace/events/sched.h
> @@ -896,6 +896,19 @@ DECLARE_TRACE(sched_set_need_resched,
>  	TP_PROTO(struct task_struct *tsk, int cpu, int tif),
>  	TP_ARGS(tsk, cpu, tif));
>  
> +/*
> + * The two trace points below may not work as expected for fair
> tasks due
> + * to delayed dequeue. See:
> + *
> https://lore.kernel.org/lkml/179674c6-f82a-4718-ace2-67b5e672fdee@amd.com/
> + */
> +DECLARE_TRACE(enqueue_task,
> +	TP_PROTO(int cpu, struct task_struct *task),
> +	TP_ARGS(cpu, task));
> +
> +DECLARE_TRACE(dequeue_task,
> +	TP_PROTO(int cpu, struct task_struct *task),
> +	TP_ARGS(cpu, task));
> +
>  #endif /* _TRACE_SCHED_H */
>  
>  /* This part must be outside protection */
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index be00629f0ba4..6367799aa023 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -2077,6 +2077,8 @@ unsigned long get_wchan(struct task_struct *p)
>  
>  void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
>  {
> +	trace_enqueue_task_tp(cpu_of(rq), p);
> +
>  	if (!(flags & ENQUEUE_NOCLOCK))
>  		update_rq_clock(rq);
>  
> @@ -2119,7 +2121,11 @@ inline bool dequeue_task(struct rq *rq, struct
> task_struct *p, int flags)
>  	 * and mark the task ->sched_delayed.
>  	 */
>  	uclamp_rq_dec(rq, p);
> -	return p->sched_class->dequeue_task(rq, p, flags);
> +	if (p->sched_class->dequeue_task(rq, p, flags)) {
> +		trace_dequeue_task_tp(cpu_of(rq), p);
> +		return true;
> +	}
> +	return false;
>  }
>  
>  void activate_task(struct rq *rq, struct task_struct *p, int flags)